NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWE8VWC6FFS417VPAFKX9B05
Run Details
Model:
Claude Sonnet 5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
9.6s
Cost:
$0.004856
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
97.63%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
48.8138%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% words of dialogue between two thieves named Molly and Bill who are planning to break into a children's party to steal all the presents. Only include the prose of the scene without any markdown or commentary.
Model response
Messages
Meta
AI
Molly slid the blueprint of the McAllister backyard across the table, jabbing a finger at the bounce house. "The presents are stacked right here, behind the pin the tail on the donkey station." Bill squinted. "There's a clown, Molly. A clown." "So?" "Clowns notice things. It's their whole deal. Big shoes, bigger eyes." "He's juggling. He won't see us." "Everyone sees the juggler, Bill, that's the point of juggling." "Fine. We wait till the piñata." "The piñata's a distraction, sure, but there's also a bouncy castle full of seven-year-olds with sugar in their veins. That's not a party, that's a stampede waiting for a reason." Molly rolled her eyes. "We dress as party clowns ourselves. Blend in." "Two grown adults in wigs, carrying an empty sack, at a six-year-old's birthday party." "It's a *big* sack. For balloons." "For presents." "For balloon-shaped presents." Bill sighed, rubbing his temples. "And when Timmy's mother asks why the clown is sweating and stealing?" "I tell her I have a gluten thing." "That doesn't even—" "Bill. Focus. Cake happens at three. We move at 2:58." He stared at her. "You've timed a toddler's cake cutting." "I time everything."
created_at
"2026-07-01T07:21:32.306Z"
7/1/2026, 7:21:32 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1678
moderation_latency
(null)
generation_time
9536
tokens_prompt
77
tokens_completion
327
native_tokens_prompt
93
native_tokens_completion
467
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"end_turn"
service_tier
"default"
usage
0.004856
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_01Jn3phTQctVUT5MWz5rakGh"
is_byok
false
latency
1677
model_permaslug
"anthropic/claude-sonnet-5-20260630"
provider_name
"Amazon Bedrock"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.17.0; linux; x64))"
http_referer
(null)
request_id
"req-1782890492-5pz5gih7xvVIjQlciuys"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782890492-gzXF1diiPbUlPtGHU0d8"
upstream_id
"msg_01Jn3phTQctVUT5MWz5rakGh"
total_cost
0.004856
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
97.63%
Matches word count
n/a
neededClean
false
words
193
0.00%
Dialogue to Total Word Ratio
Ratio: 83.33%, Deviation: 33.33%
neededClean
false
wordsTotal
198
wordsDialogue
165
48.8138%